Combining interval time series forecasts. A first step in a long way (research agenda). (English) Zbl 1470.62132

Summary: We observe every day a world more complex, uncertain, and riskier than the world of yesterday. Consequently, having accurate forecasts in economics, finance, energy, health, tourism, and so on; is more critical than ever. Moreover, there is an increasing requirement to provide other types of forecasts beyond point ones such as interval forecasts. After more than 50 years of research, there are two consensuses, “combining forecasts reduces the final forecasting error” and “a simple average of several forecasts often outperforms complicated weighting schemes”, which was named “forecast combination puzzle (FCP)”. The introduction of interval-valued time series (ITS) concepts and several forecasting methods has been proposed in different papers and gives answers to some big data challenges. Hence, one main issue is how to combine several forecasts obtained for one ITS. This paper proposes some combination schemes with a couple or various ITS forecasts. Some of them extend previous crisp combination schemes incorporating as a novelty the use of Theil’s U. The FCP under the ITS forecasts framework will be analyzed in the context of different accuracy measures and some guidelines will be provided. An agenda for future research in the field of combining forecasts obtained for ITS will be outlined.


62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62M20 Inference from stochastic processes and prediction
60K50 Anomalous diffusion models (subdiffusion, superdiffusion, continuous-time random walks, etc.)
62P05 Applications of statistics to actuarial sciences and financial mathematics
91B84 Economic time series analysis


Apache Spark
Full Text: DOI


[1] Aladag, C. H., Egrioglu, E. & Yolcu, U. (2010), ‘Forecast combination by using artificial neural networks’,Neural Processing Letters32(3), 269-276. · Zbl 1372.62039
[2] Armstrong, J. S. (2001),Combined forecasts. In Principles of Forecasting: A Handbook for Researchers and Practitioners, Kluwer Academic Publishers, Norwell, MA.
[3] Arroyo, J., Espínola, R. & Maté, C. (2011a), ‘Different approaches to forecast interval time series:a comparison in finance’,Computational Economics 37(2), 169-191. · Zbl 1206.91087
[4] Arroyo, J., Espínola, R. & Maté, C. (2011b), ‘Different approaches to forecast interval time series:a comparison in finance’,Computational Economics 37(2), 169-191. · Zbl 1206.91087
[5] Arroyo, J., González-Rivera, G. & Maté, C. (2010), ‘Forecasting with interval and histogram data. some financial applications’,Handbook of empirical economics and financepp. 247-280.
[6] Arroyo, J. & Maté, C. (2006), Introducing interval time series: accuracy measures, in‘Compstat, proceedings in computational statistics’, Heidelberg: PhysicaVerlag, pp. 1139-1146.
[7] Arroyo, J. & Maté, C. (2009), ‘Forecasting histogram time series with k-nearest neighbours methods’,International Journal of Forecasting25(1), 192-07.
[8] Atiya, A. F. (2020), ‘Why does forecast combination work so well?’,International Journal of Forecasting36(1), 197-200.
[9] Combining ITS Forecasts153
[10] Avci, E., Ketter, W. & van Heck, E. (2018), ‘Managing electricity price modeling risk via ensemble forecasting: The case of turkey’,Energy Policy123, 390-403.
[11] Bassetti, F., Casarin, R. & Ravazzolo, F. (2020), Density forecasting,in ‘Macroeconomic Forecasting in the Era of Big Data’, Springer, pp. 465-494.
[12] Bates, J. M. & Granger, C. W. (1969), ‘The combination of forecasts’,Journal of the Operational Research Society20(4), 451-468.
[13] Billard, L. & Diday, E. (2003), ‘From the statistics of data to the statistics of knowledge: Symbolic data analysis’,Journal of the American Statistical Association98(462), 470-487.
[14] Billard, L. & Diday, E. (2006),Symbolic Data Analysis: Conceptual Statistics and Data Mining John Wiley, Chichester. · Zbl 1117.62002
[15] Blanco-Fernández, A., Corral, N. & González-Rodríguez, G. (2011), ‘Estimation of a flexible simple linear model for interval data based on set arithmetic’, Computational Statistics & Data Analysis55(9), 2568-2578. · Zbl 1464.62030
[16] Buansing, T. T., Golan, A. & Ullah, A. (2020), ‘An information-theoretic approach for forecasting interval-valued sp500 daily returns’,International Journal of Forecasting36, 800-813.
[17] Chen, Y., Chen, H., Gorkhali, A., Lu, Y., Ma, Y. & Li, L. (2016), ‘Big data analytics and big data science: a survey’,Journal of Management Analytics 3(1), 1-42.
[18] Clemen,R. T. (1989),‘Combining forecasts:A review and annotated bibliography’,International Journal of Forecasting5(4), 559-583.
[19] de Menezes, L., Bunn, D. & Taylor, J. (2000), ‘Review of guidelines for the use of combined forecasts’,European Journal of Operational Research120(1), 190-204. · Zbl 0962.91531
[20] den Butter, F. A. & Jansen, P. W. (2013), ‘Beating the random walk:a performance assessment of long-term interest rate forecasts’,Applied Financial Economics23(9), 749-765.
[21] Dickinson, J. (1975), ‘Some comments on the combination of forecasts’,Journal of the Operational Research Society26(1), 205-210. · Zbl 0312.62068
[22] Diebold, F. X. & Mariano, R. S. (1995), ‘Comparing predictive accuracy’,Journal of Business & Economic Statistics13(3), 253-263.
[23] Fama, E. F. (1995), ‘Random walks in stock market prices’,Financial Analysts Journal51(1), 75-80.
[24] Fama, E. F. & Blume, M. E. (1966), ‘Filter rules and stock-market trading’,The Journal of Business39(1), 226-41.
[25] Galicia, A., Talavera-Llames, R., Troncoso, A., Koprinska, I. & Martínez-Álvarez, F. (2019), ‘Multi-step forecasting for big data time series based on ensemble learning’,Knowledge-Based Systems163, 830-841.
[26] 154Carlos G. Maté
[27] Gao, Y., Shang, H. L. & Yang, Y. (2019), ‘High-dimensional functional time series forecasting: An application to age-specific mortality rates’,Journal of Multivariate Analysis170, 232-43. · Zbl 1415.62093
[28] García-Ascanio, C. & Maté, C. (2010), ‘Electric power demand forecasting using interval time series:A comparison between var and imlp’,Energy Policy 38(2), 715-725.
[29] Genre, V., Kenny, G., Meyler, A. & Timmermann, A. (2013), ‘Combining expert forecasts: Can anything beat the simple average?’,International Journal of Forecasting29(1), 108-121.
[30] Gibbs, C. G. (2017), ‘Forecast combination, non-linear dynamics, and the macroeconomy’,Economic Theory63(3), 653-686. · Zbl 1405.91441
[31] Glennon, D., Kiefer, H. & Mayock, T. (2018), ‘Measurement error in residential property valuation: An application of forecast combination’,Journal of Housing Economics41, 1-9.
[32] Gneiting, T. (2011), ‘Making and evaluating point forecasts’,Journal of the American Statistical Association106(494), 746-762. · Zbl 1232.62028
[33] Gneiting, T. & Katzfuss, M. (2014), ‘Probabilistic forecasting’,Annual Review of Statistics and Its Application1, 125-151.
[34] Hallman, J. & Kamstra, M. (1989), ‘Combining algorithms based on robust estimation techniques and co-integrating restrictions’,Journal of Forecasting 8(3), 189-198.
[35] Han, A., Hong, Y., Lai, K. & Wang, S. (2008), ‘Interval time series analysis with an application to the sterling-dollar exchange rate’,Journal of Systems Science and Complexity21(4), 550-565. · Zbl 1177.91113
[36] Han, A., Lai, K. K., Wang, S. & Xu, S. (2012), ‘An interval method for studying the relationship between the australian dollar exchange rate and the gold price’,Journal of Systems Science and Complexity25(1), 121-132. http://link.springer.com/article/10.1007/s11424-012-8116-x · Zbl 1251.93020
[37] Hendry, D. F. & Clements, M. P. (2004), ‘Pooling of forecasts’,The Econometrics Journal7(1), 1-31. · Zbl 1053.62104
[38] Hsu, H.-L. & Wu, B. (2008), ‘Evaluating forecasting performance for interval data’, Computers & Mathematics with Applications56(9), 2155-163. · Zbl 1165.62341
[39] Hyndman, R. J. & Koehler, A. B. (2006), ‘Another look at measures of forecast accuracy’,International journal of forecasting22(4), 679-688.
[40] Hyndman, R. J. & Shang, H. L. (2009), ‘Forecasting functional time series’, Journal of the Korean Statistical Society38(3), 199-11. · Zbl 1293.62267
[41] Irpino, A. & Verde, R. (2008), ‘Dynamic clustering of interval data using a wasserstein-based distance’,Pattern Recognition Letters29(11), 1648-1658. · Zbl 1147.62054
[42] Combining ITS Forecasts155
[43] Kao, C.-H., Nakano, J., Shieh, S.-H., Tien, Y.-J., Wu, H.-M., Yang, C.-K. & Chen, C.-h. (2014), ‘Exploratory data analysis of interval-valued symbolic data with matrix visualization’,Computational Statistics & Data Analysis79, 14-29. · Zbl 06984052
[44] Kourentzes, N., Barrow, D. & Petropoulos, F. (2019), ‘Another look at forecast selection and combination:Evidence from forecast pooling’,International Journal of Production Economics209, 226-235.
[45] Kubica, B. J. & Malinowski, K. (2006), Interval random variables and their application in queueing systems with long-tailed service times.,in‘SMPS’, Springer, pp. 393-403. · Zbl 1109.60002
[46] Kwiatkowski, D., Phillips, P., Schmidt, P. & Shin, Y. (1992), ‘Testing the null hypothesis of stationarity against the alternative of a unit root: how sure are we that economic time series have a unit root?’,Journal of Econometrics54(13), 159-178. · Zbl 0871.62100
[47] Le-Rademacher, J. & Billard, L. (2012), ‘Symbolic covariance principal component analysis and visualization for interval-valued data’,Journal of Computational and Graphical Statistics21(2), 413-432.
[48] Li, H., Wang, J., Lu, H. & Guo, Z. (2018), ‘Research and application of a combined model based on variable weight for short term wind speed forecasting’, Renewable Energy116, 669-684.
[49] Lima Neto, E. & De Carvalho, F. (2010), ‘Constrained linear regression models for symbolic interval-valued variables’,Computational Statistics and Data Analysis 54, 333-347. · Zbl 1464.62055
[50] Maia, A. L. S. & de Carvalho, F. d. A. (2011), ‘Holts exponential smoothing and neural network models for forecasting interval-valued time series’,International Journal of Forecasting27(3), 740-759.
[51] Maia, A. L. S., de Carvalho, F. d. A. & Ludermir, T. B. (2008), ‘Forecasting models for interval-valued time series’,Neurocomputing71(16-18), 3344-3352.
[52] Makridakis, S., Spiliotis, E. & Assimakopoulos, V. (2020), ‘The m4 competition: 100,000 time series and 61 forecasting methods’,International Journal of Forecasting36(1), 54-74.
[53] Maté, C. (2012), ‘The bayesian model averaging approach for interval-valued data. 3 rd workshop in symbolic data analysis’, pp. 47-48.
[54] Maté, C. G. (2011), ‘A multivariate analysis approach to forecasts combination. application to foreign exchange (fx) markets’,Revista Colombiana de Estadística 34(2), 347-375.
[55] Moral-Benito, E. (2015), ‘Model averaging in economics: An overview’,Journal of Economic Surveys29(1), 46-75.
[56] Muñoz, A., Maté, C., Arroyo, J. & Sarabia, A. (2007), ‘iMLP: applying multilayer perceptrons to interval-valued data’,Neural Processing Letters25(2), 157-169.
[57] 156Carlos G. Maté
[58] Naseer, M., bin Tariq, Y. et al. (2015), ‘The efficient market hypothesis: A critical review of the literature’,IUP Journal of Financial Risk Management12(4), 48- 63.
[59] Nelson, C. R. & Plosser, C. R. (1982), ‘Trends and random walks in macroeconomic time series: some evidence and implications’,Journal of Monetary Economics 10(2), 139-162.
[60] Noirhomme-Fraiture, M. & Brito, P. (2011), ‘Far beyond the classical data models: symbolic data analysis’,Statistical Analysis and Data Mining: the ASA Data Science Journal4(2), 157-170. · Zbl 07260275
[61] Ordiano, J. Á. G., Bartschat, A., Ludwig, N., Braun, E., Waczowicz, S., Renkamp, N., Peter, N., Düpmeier, C., Mikut, R. & Hagenmeyer, V. (2018), ‘Concept and benchmark results for big data energy forecasting based on apache spark’, Journal of Big Data5(1), 11.
[62] Phillips, P. C. & Perron, P. (1988), ‘Testing for a unit root in time series regression’, Biometrika75(2), 335-346. · Zbl 0644.62094
[63] Ramos-Guajardo, A. B., González-Rodríguez, G. & Colubi, A. (2020), ‘Testing the degree of overlap for the expected value of random intervals’,International Journal of Approximate Reasoning119, 1-19. · Zbl 1440.62079
[64] Rapach, D. & Zhou, G. (2013), Forecasting stock returns,in‘Handbook of economic forecasting’, Vol. 2, Elsevier, pp. 328-383.
[65] Riddington, G. (1993), ‘Time varying coefficient models and their forecasting performance’,Omega21(5), 573-583.
[66] Rodrigues, P. M. & Salish, N. (2015), ‘Modeling and forecasting interval time series with threshold models’,Advances in Data Analysis and Classification9(1), 41- 57. · Zbl 1414.62076
[67] Sarno, L. & Valente, G. (2005), ‘Empirical exchange rate models and currency risk: Some evidence from density forecasts’,Journal of International Money and Finance24(2), 363-385.
[68] Shaub, D. (2020), ‘Fast and accurate yearly time series forecasting with forecast combinations’,International Journal of Forecasting36(1), 116-120.
[69] Sinova, B., Casals, M. R., Colubi, A. & Gil, M. Á. (2010), The median of a random interval,in‘Combining Soft Computing and Statistical Methods in Data Analysis’, Springer, pp. 575-583.
[70] Sinova, B., Colubi, A., González-Rodrı, G. et al. (2012), ‘Interval arithmeticbased simple linear regression between interval data: Discussion and sensitivity analysis on the choice of the metric’,Information Sciences199, 109-124. · Zbl 06094584
[71] Sinova, B. & Van Aelst, S. (2015), ‘On the consistency of a spatial-type intervalvalued median for random intervals’,Statistics & Probability Letters100, 130- 136. · Zbl 1328.62300
[72] Combining ITS Forecasts157
[73] Smith, J. & Wallis, K. F. (2009), ‘A simple explanation of the forecast combination puzzle’,Oxford Bulletin of Economics and Statistics71(3), 331-355.
[74] Song, H. & Liu, H. (2017), Predicting tourist demand using big data,in‘Analytics in smart tourism design’, Springer, pp. 13-29.
[75] Stock, J. H. & Watson, M. W. (2004), ‘Combination forecasts of output growth in a seven-country data set’,Journal of Forecasting23(6), 405-430.
[76] Stock, J. H. & Watson, M. W. (2006), ‘Forecasting with many predictors’, Handbook of economic forecasting1, 515-554.
[77] Tay, A. S. & Wallis, K. F. (2000), ‘Density forecasting: a survey’,Journal of Forecasting19(4), 235-54.
[78] Thomson, M. E., Pollock, A. C., Önkal, D. & Gönül, M. S. (2019), ‘Combining forecasts: Performance and coherence’,International Journal of Forecasting 35(2), 474-484.
[79] Timmermann,A. (2006),‘Forecast combinations’,Handbook of Economic Forecasting1, 135-196.
[80] Wang, J. & Wu, J. J. (2012), ‘The taylor rule and forecast intervals for exchange rates’,Journal of Money, Credit and banking44(1), 103-144.
[81] Winkler, R. L. & Clemen, R. T. (1992), ‘Sensitivity of weights in combining forecasts’,Operations Research40(3), 609-614. · Zbl 0850.62694
[82] Zhang, W., Liu, J., Cho, C. & Han, X. (2015), ‘A hybrid parameter identification method based on bayesian approach and interval analysis for uncertain structures’,Mechanical Systems and Signal Processing60, 853-865.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.